Project Leads: Prof. RAS Denis Sidorov (ESI SB RAS) and Prof. Fang Liu (CSU)
Wind power systems are characterized by generation variability. The project deals with the integration of wind energy systems using new energy storage control algorithms, as well as forecasting models of electric load and wind generation. Effective storage control models are proposed, which are expressed in terms of nonlinear systems of evolutionary Volterra nonlinear integral equations of the first kind that allow to take into account the efficiency and state-of-change reduction and also able to effectively determine the active mass of battery degradation. To solve these nonlinear systems, effective numerical methods based on a modified Newton-Kantorovich iterative process and spline collocation are proposed. A general convergence theorem for the method is proved. An estimate for the rate of convergence is obtained. The theoretical basement of a methodology and software have been proposed for storage control and for wind speed and power forecasting using fuzzy Takagi-Sugeno models and electrical loads forecasting. Forecasting models employ the deep learning based on convolutional-based bidirectional gated recurrent unit and tested on electric load and air pollution datasets. The project will improve the efficiency of AC/DC micro grids with storage system in the nature protection zone of Lake Baikal.
The evolutionary integral dynamical models of storage systems are addressed. Such models are based on systems of weakly regular nonlinear Volterra integral equations with piecewise smooth kernels. These equations can have non-unique solutions that depend on free parameters. The objective of this paper was two-fold. First, the iterative numerical method based on the modified Newton–Kantorovich iterative process is proposed for a solution of the nonlinear systems of such weakly regular Volterra equations. Second, the proposed numerical method was tested both on synthetic examples and real world problems related to the dynamic analysis of microgrids with energy storage systems.
Oscillation is one of the most important factors that affect the safety and stability of power system. In a power system, there may be multiple types of oscillation signal occurring at the same time. In this paper, a method based on improved variational modal decomposition (VMD) algorithm is proposed to identify the mode of broad-band oscillation signal. First, different types of oscillation are separated from broad-band oscillation signal by band pass filter. And then the modal signals are extracted from the filtered signals by improved VMD method. Finally, the parameters of the modal signals are identified by prony algorithm. The simulation shows that the method can extract the modal signals from broad-band signal and identify the parameters accurately
Tourism development in ecologically vulnerable areas like the lake Baikal region in Eastern Siberia is a challenging problem. To this end, the dynamical models of AC/DC hybrid isolated power system consisting of four power grids with renewable generation units and energy storage systems are proposed using the advanced methods based on deep reinforcement learning and integral equations. First, the wind and solar irradiance potential of several sites on the lake Baikal’s banks is analyzed as well as the electric load as a function of the climatic conditions. The optimal selection of the energy storage system components is supported in online mode. The approach is justified using the retrospective meteorological datasets. Such a formulation will allow us to develop a number of valuable recommendations related to the optimal control of several autonomous AC/DC hybrid power systems with different structures, equipment composition and kind of AC or DC current. Developed approach provides the valuable information at different stages of AC/DC hybrid power systems projects development with stand-alone hybrid solar-wind power generation systems.
Forecasting problems exist widely in our life. Its purpose is to enable decision makers to make effective responses to future changes. The traditional prediction methods based on probability and statistics cannot guarantee the accuracy of multivariable dynamic prediction under the background of high randomness and big data. In recent years, with the improvement of hardware computing ability and the large-scale increase of training data, deep learning has been widely applied in the field of forecasting. This paper focuses on the analysis of the application of recurrent neural networks (RNN), an advanced algorithm in deep learning, in the forecasting task. The forecasting models based on long short-term memory (LSTM) and gated recurrent unit (GRU) were established respectively, and the real data of power load and air pollution were verified. Compared with traditional machine learning algorithms, the simulation proves the superiority of the forecasting model based on RNN.
The necessary and sufficient conditions of existence of the nonlinear operator equations’ branches of solutions in the neighbourhood of branching points are derived. The approach is based on the reduction of the nonlinear operator equations to finite-dimensional problems. Methods of nonlinear functional analysis, integral equations, spectral theory based on index of Kronecker-Poincaré, Morse-Conley index, power geometry and other methods are employed. Proposed methodology enables justification of the theorems on existence of bifurcation points and bifurcation sets in the nonstandard models. Formulated theorems are constructive. For a certain smoothness of the nonlinear operator, the asymptotic behaviour of the solutions is analysed in the neighbourhood of the branch points and uniformly converging iterative schemes with a choice of the uniformization parameter enables the comprehensive analysis of the problems details. General theorems and effectiveness of the proposed methods are illustrated on the nonlinear integral equations.
The objective of this editorial is to overview the content of the special issue “Machine Learning for Energy Systems”. This special issue collects innovative contributions addressing the top challenges in energy systems development, including electric power systems, heating and cooling systems, and gas transportation systems. The special attention is paid to the non-standard mathematical methods integrating data-driven black box dynamical models with classic mathematical and mechanical models. The general motivation of this special issue is driven by the considerable interest in the rethinking and improvement of energy systems due to the progress in heterogeneous data acquisition, data fusion, numerical methods, machine learning, and high-performance computing. The editor of this special issue has made an attempt to publish a book containing original contributions addressing theory and various applications of machine learning in energy systems’ operation, monitoring, and design. The response to our call had 27 submissions from 11 countries (Brazil, Canada, China, Denmark, Germany, Russia, Saudi Arabia, South Korea, Taiwan, UK, and USA), of which 12 were accepted and 15 were rejected. This issue contains 11 technical articles, one review, and one editorial. It covers a broad range of topics including reliability of power systems analysis, power quality issues in railway electrification systems, test systems of transformer oil, industrial control problems in metallurgy, power control for wind turbine fatigue balancing, advanced methods for forecasting of PV output power as well as wind speed and power, control of the AC/DC hybrid power systems with renewables and storage systems, electric-gas energy systems’ risk assessment, battery’s degradation status prediction, insulators fault forecasting, and autonomous energy coordination using blockchain-based negotiation model. In addition, review of the blockchain technology for information security of the energy internet is given. We believe that this special issue will be of interest not only to academics and researchers, but also to all the engineers who are seriously concerned about the unsolved problems in contemporary power engineering, multi-energy microgrids modeling.
本文的目的是对特刊“Machine Learning for Energy Systems”的内容进行综述。该特刊收集了解决能源系统发展中重要挑战的创新成果，包括电力系统、加热和冷却系统以及天然气运输系统，重点关注数据驱动的黑箱动力学模型与经典数学和力学模型相结合的非标准数学方法。随着异构数据采集、数据融合、数值方法、机器学习和高性能计算方面的进展，人们对能源系统的重新思考和改进产生了相当大的兴趣，这也是本特刊的总体动机。本特刊的编辑考虑出版一本基于原始文稿的书籍，解决机器学习在能源系统运行、监控和设计方面的理论及各类应用问题。本刊征文收到了来自11个国家/地区（巴西、加拿大、中国、丹麦、德国、俄罗斯、沙特阿拉伯、韩国、台湾、英国和美国）的27篇投稿，接收12篇，拒稿15篇。本刊包含11篇技术文章、1篇综述和1篇评论，涵盖了广泛的主题，包括电力系统可靠性分析、铁路电气化系统电能质量问题、变压器油的测试系统、冶金工业控制问题、风机疲劳平衡的功率控制、光伏及风速、风电功率先进预测方法、含新能源发电与储能的AC/DC混合电力系统控制、电-气能源系统风险评估、电池退化状态预测、绝缘体故障预测及基于区块链协商模型的自主能源协调等。此外，还对用于能源互联网信息安全的区块链技术进行了综述。我们相信，本特刊不仅会引起学者和研究人员的兴趣，也会吸引所有关注当代电力工程、多能源微电网建模领域待解决难题的工程师。
Finding the optimal parameters and functions of iterative methods is among the main problems of the Numerical Analysis. For this aim, a technique of the stochastic arithmetic (SA) is used to control of accuracy on Taylor-collocation method for solving first kind weakly regular integral equations (IEs). Thus, the CESTAC method is applied and instead of usual mathematical software the CADNA library is used. Also, the convergence theorem of presented method is illustrated. In order to apply the CESTAC method we will prove a theorem that it will be our licence to use the new termination criterion instead of traditional absolute error. By using this theorem we can show that number of common significant digits (NCSDs) between two successive approximations are almost equal to NCSDs between exact and numerical solution. Finally, some examples are solved by using the Taylor-collocation method based on the CESTAC method. Several tables of numerical solutions based on the both arithmetics are presented. Comparison between number of iterations are demonstrated by using the floating point arithmetic (FPA) for different values of epsilon.
This volume collects innovative contributions addressing the top challenges in energy systems development, including electric power systems, heating and cooling systems, and gas transportation systems. The special attention is paid to the non-standard mathematical methods integrating data-driven black box dynamical models with classic mathematical and mechanical models. The general motivation of this volume is driven by the considerable interest in the rethinking and improvement of energy systems due to the progress in heterogeneous data acquisition, data fusion, numerical methods, machine learning, and high-performance computing. This volume covers a broad range of topics including reliability of power systems analysis, power quality issues in railway electrification systems, test systems of transformer oil, industrial control problems in metallurgy, power control for wind turbine fatigue balancing, advanced methods for forecasting of PV output power as well as wind speed and power, control of the AC/DC hybrid power systems with renewables and storage systems, electric-gas energy systems’ risk assessment, battery’s degradation status prediction, insulators fault forecasting, and autonomous energy coordination using blockchain-based negotiation model. In addition, review of the blockchain technology for information security of the energy internet is given. We believe that this book will be of interest not only to academics and researchers, but also to all the engineers who are seriously concerned about the unsolved problems in contemporary power engineering, multi-energy microgrids modeling.
The article deals with integrated power systems with renewable sources of generation in the settlements of Lake Baikal. The analysis of natural and climatic features in relation to the wind potential of the specified area is carried out. The construction of wind forecast using machine learning algorithms is considered. Global NWP forecast and machine learning model to achieve acceptable accuracy are combined. This forecast is used in the Volterra model to determine the operating parameters of energy storage units, in which the efficiency is a nonlinear function of the charge level, age and external operating conditions, i.e. the process of charging and discharging energy storage systems is described using Volterra integral equations. Such formulation of the problem will allow for the design of power systems to use a number of valuable recommendations regarding the optimal management of energy storage systems with several integrated power systems. The numerical solution of the proposed Volterra integral model was obtained using the spline collocation method.